Uploaded September 2026 | Updated November 2026, 3 hours ago
セッションの 紹 介
レガシー アプリケーションの なモダナイゼーションは 変 革 の 第 一 歩
AIシステムを 環 境 安 定 運 用 継 続 監 視 迅 速 障 害 対 応 高 信 頼 性 現 仕 組 不 可 欠
GitHub Copilotを 用 自 己 修 復 型 エージェントや 運 用 インテリジェンスを AIシステム 運 用 紹 介
AIを 運 用 負 荷 軽 減 信 頼 性 拡 張 性 えたAI 運 用 実 現 なアプローチを 学
学 習 内 容
- Copilot Modernize CLI のレガシーアプリケーションの 評 価 やアップグレードを
- Stacked Pull Requests 自 動 マイグレーションのレビューを 率
- Azure SRE Agent 診 断 検 証 修 復 策
- トークン 効 率 復 旧 時 間 受 け 入 れ 率 運 用 効 果 可 視 化 追 跡
- Azure SRE Agent
- Copilot App Modernization Agent
- Modernize CLI
- Stacked Pull Requests
- Human - in - the - Loop ガバナンスパターン
取 り 組 んでいるチーム
- 環 境 でAIシステムを 運 用 開 発 者 やプラットフォームエンジニア
- エージェント 支 援 障 害 対 応 運 用 改 善 検 討 しているSRE ・ DevOpsチーム
- 拡 張性 信 頼 性 AI 運 用 実 現 指 技 術 リーダー
講 演 者
Yurie
[eventID:27638]
セッションの 紹 介
レガシー アプリケーションの なモダナイゼーションは 変 革 の 第 一 歩
AIシステムを 環 境 安 定 運 用 継 続 監 視 迅 速 障 害 対 応 高 信 頼 性 現 仕 組 不 可 欠
GitHub Copilotを 用 自 己 修 復 型 エージェントや 運 用 インテリジェンスを AIシステム 運 用 紹 介
AIを 運 用 負 荷 軽 減 信 頼 性 拡 張 性 えたAI 運 用 実 現 なアプローチを 学
学 習 内 容
- Copilot Modernize CLI のレガシーアプリケーションの 評 価 やアップグレードを
- Stacked Pull Requests 自 動 マイグレーションのレビューを 率
- Azure SRE Agent 診 断 検 証 修 復 策
- トークン 効 率 復 旧 時 間 受 け 入 れ 率 運 用 効 果 可 視 化 追 跡
- Azure SRE Agent
- Copilot App Modernization Agent
- Modernize CLI
- Stacked Pull Requests
- Human - in - the - Loop ガバナンスパターン
取 り 組 んでいるチーム
- 環 境 でAIシステムを 運 用 開 発 者 やプラットフォームエンジニア
- エージェント 支 援 障 害 対 応 運 用 改 善 検 討 しているSRE ・ DevOpsチーム
- 拡 張性 信 頼 性 AI 運 用 実 現 指 技 術 リーダー
講 演 者
Yurie
[eventID:27638]
![Afinal, o que é Fabric IQ?
Fabric IQ parece importante, mas o que ele realmente faz?
Vamos explicar como ele usa o contexto do negócio para ajudar a IA a entender seus dados, como se conecta ao restante do Fabric e como isso pode funcionar em um cenário real.
Para mais informações sobre o Data Days e tudo o que ele tem a oferecer, acesse https://aka.ms/DataDays
📌 Este evento faz parte de uma série. Saiba mais aqui: https://aka.ms/AIatWork/UnderstandIt/y
#MicrosoftReactor #LearnConnectBuild #Fabric #AI #DataDays
[eventID:27731] Afinal, o que é Fabric IQ?](https://i.ytimg.com/vi/3eQy8522XIc/mqdefault.jpg)
![AI-Powered Developer Productivity with GitHub Copilot and VS Code
AI-assisted development is transforming how engineers build and maintain software.
This session showcases practical workflows using GitHub Copilot and VS Code, covering code generation, debugging, testing, documentation, and productivity techniques you can apply in your day-to-day work.
Attendees will learn how to enhance their development process with AI while maintaining efficiency, quality, and responsible practices.
Key takeaways:
- Effective prompting for software development
- AI-assisted debugging and testing
- Developer productivity workflows
- Responsible AI usage practices
📌 This is part of a series, learn more here: https://aka.ms/ProdReadySystems/series
0:00 Session Introduction and Housekeeping
2:53 Introduction to Responsible AI in Engineering (Ram)
4:59 Assessing AI Capabilities vs. Necessary Evidence
6:48 Useful Engineering Workflows for AI
8:41 Practical Example: Query Generation Issues
11:05 Recommended Workflow for AI Tasks
13:35 Privacy, Data Handling, and Fine-Tuning
15:22 Human Oversight, Evidence, and Accountability
17:41 Ensuring Reliability and Evaluation
19:36 Transparency and Disclosure
21:54 Permissions, Recovery, and Conclusion
26:36 Introduction to Building Production-Grade Agentic AI (Anamaka)
31:38 Query Generation Workloads (NL2KQL and Graph)
33:47 Why Retrieval-Augmented Generation (RAG) over Fine-Tuning
36:00 Context Retrieval and Schema Validation
43:48 Building an Incident Investigation (DRI) Agent
46:13 Prompt-Based Agent Architecture
49:56 Cost and Context Window Challenges
54:55 Moving to Agentic Workflows for Reliability
58:56 Summary: Prompt-Based vs. Workflow Agents
1:03:04 Closing Remarks and Feedback
[eventID:27361] AI-Powered Developer Productivity with GitHub Copilot and VS Code](https://i.ytimg.com/vi/3j0y2ExcF5o/mqdefault.jpg)
![Azure Incident Retrospective: AOAI/Foundry-Failures in Sweden Central (ID:7QL5-Z50)
On 29 September 2026, the Azure platform experienced a service incident (Tracking ID: 7QL5-Z50) which caused AOAI / Foundry – intermittent failures in Sweden Central.
After publishing the Post Incident Review (PIR) we invited impacted customers and partners to join this Teams Live Event to be part of a discussion with our engineering leaders and experts – to learn more about the incident, how we responded, and what we learned.
Customers who participated in the live event also had an opportunity to get any questions about the incident answered, through a Live Q&A moderated by our engineering subject matter experts.
Stay informed during issues
– configure Service Health alerts for notifications and invites: https://www.aka.ms/ASH-docs
Learn from previous events
– Health history in Azure Service Health shows impact to your services: https://www.aka.ms/ASH-portal
Prepare for the unexpected
– learn more about steps you can take to prepare for cloud incidents: https://www.aka.ms/IncidentReadiness
[eventID:27782] Azure Incident Retrospective: AOAI/Foundry-Failures in Sweden Central (ID:7QL5-Z50)](https://i.ytimg.com/vi/3nveXKuAYdg/mqdefault.jpg)
![De “isso é legal” para “eu realmente poderia usar isso”
É fácil assistir a uma demo de IA e pensar: “Legal.” Transformar aquilo em algo realmente útil no trabalho é outra história.
Nesta sessão, vamos começar com um problema real e pensar juntos em como transformá-lo em um cenário de IA que valha a pena explorar.
Para mais informações sobre o Data Days e tudo o que ele tem a oferecer, acesse https://aka.ms/DataDays
📌 Este evento faz parte de uma série. Saiba mais aqui: https://aka.ms/AIatWork/UnderstandIt/y
#MicrosoftReactor #LearnConnectBuild #Fabric #AI #DataDays
[eventID:27730] De “isso é legal” para “eu realmente poderia usar isso”](https://i.ytimg.com/vi/4QAx_Lji-6Q/mqdefault.jpg)
![Bicep 102: Beyond the Basics, Scaling Your Infrastructure as Code with Bicep
One Bicep file works well for one team and one environment, but it gets hard to share, review, and keep consistent once several teams and environments depend on it.
This session picks up where Bicep 101 ends and shows how to scale a Bicep codebase. I am a product manager at Microsoft on Azure Bicep and owning Deployment Stacks. Bicep is Azures native infrastructure as code language and a stateless alternative to Terraform, so there is no state file to store, secure, or keep in sync.
In the demo I split a single Bicep file into modules, replace hand-written resources with Azure Verified Modules, and publish a shared module to a private registry so other teams use the same version. I add a parameters file for each environment and user-defined types, so a wrong value fails before anything is deployed, and set linter rules for the whole repository in bicepconfig.json. I then use GitHub Copilot to bring resources that were built by hand into the same code and add a GitHub Actions pipeline that runs Stacks
What-If before every deployment, which confirms that adopting those resources changes nothing in Azure. The result is Bicep code that many teams can share and deploy the same way. Everything runs live from VS Code, GitHub, and the Azure CLI. What attendees will learn:
- How to structure Bicep with modules, Azure Verified Modules, and a private registry that several teams can share.
- How to keep environments consistent with parameters files, user-defined types, and linter rules.
- How to bring hand-built resources into code with GitHub Copilot and check every deployment with Stacks What-If.
[eventID:27836] Bicep 102: Beyond the Basics, Scaling Your Infrastructure as Code with Bicep](https://i.ytimg.com/vi/5iht3COlGSY/mqdefault.jpg)
![AI-Assisted Linux Operations on Azure: Deploy, Observe, Troubleshoot
AI on Linux is only part of the story.
In this demo-led session, Karl Abbott explores how AI can assist with operating Linux environments on Azure.
Join this demo-led session exploring AI-assisted Linux operations on Azure.
Follow a real-world workflow as an application is deployed, monitored, intentionally disrupted, and troubleshot with AI assistance.
See GitHub Copilot in action and explore how Azure agents can complement the operational toolkit.
Leave with practical ideas for bringing AI into day-to-day Linux operations, from deployment and observability to troubleshooting.
[eventID:27670] AI-Assisted Linux Operations on Azure: Deploy, Observe, Troubleshoot](https://i.ytimg.com/vi/5jzbX-qSDZw/mqdefault.jpg)
![Ship with AI: AI로 완성하는 코드 리뷰부터 보안, 배포까지
세션 소개
소프트웨어 개발은 코드 작성에서 끝나지 않습니다. 안정적이고 안전한 애플리케이션을 대규모로 제공하려면 개발 전 과정에서 일관된 품질과 신뢰성을 확보해야 합니다.
이번 세션에서는 코드 리뷰와 보안 검증부터 CI/CD, 자동 병합까지 실제 개발 워크플로우에 AI를 적용하는 방법을 살펴봅니다. 라이브 데모를 통해 AI가 개발 품질을 높이고 보안을 강화하며, 개발 전 과정의 일관성을 유지하는 방법을 확인할 수 있습니다. 또한 AI 기반 애플리케이션과 에이전트 기반 시스템을 더욱 안정적으로 배포하는 방법도 소개합니다.
이런 내용을 다룹니다
* AI를 활용한 코드 리뷰 및 개발 품질 향상
* 보안 및 컴플라이언스 워크플로우에 AI를 적용하는 방법
* 최신 CI/CD 방식을 활용한 배포 프로세스 자동화
* AI 기반 애플리케이션의 안정적인 대규모 배포 전략
주요 기술
* GitHub Copilot
* Code Review Agent
* Auto Merge
* GitHub Actions (CI/CD)
* AI 기반 보안 검토
* 개발 라이프사이클 전반의 자동화
추천 대상
* 코드 품질과 배포를 담당하는 개발자
* CI/CD 워크플로우를 운영하는 DevOps 및 플랫폼 엔지니어
* AI 기반 애플리케이션을 개발하는 엔지니어링 팀
* AI를 활용한 코드 리뷰, 보안 검증 및 소프트웨어 배포에 관심 있는 분
발표자
업데이트 예정
(00:00:00) 오프닝 및 세션 소개
(00:02:16) 발표자 소개 및 AI 개발 흐름의 중요성
(00:05:47) AI 개발 생산성과 신뢰 격차 문제
(00:07:56) 소프트웨어 공급망 보안의 중요성
(00:12:45) AI 기반 개발 파이프라인 개요
(00:13:39) 효과적인 이슈 관리 및 컨텍스트 정의
(00:16:31) PR(Pull Request)을 통한 검토와 경계 설정
(00:19:45) 자동 수정 및 병합 전략
(00:22:38) 데모: UI 개선 및 에이전트 활용
(00:25:21) 클라우드 에이전트의 작동 과정 지켜보기
(00:29:53) 코드 리뷰 및 Copilot 활용
(00:32:00) CI/CD 워크플로우와 보안 검증
(00:33:22) 코드 수정 및 실패 대응 전략
(00:46:17) 전사적 AI 거버넌스 및 표준화 사례
(00:49:50) 결론 및 향후 AI 활용 전략
[eventID:27481] Ship with AI: AI로 완성하는 코드 리뷰부터 보안, 배포까지](https://i.ytimg.com/vi/5lLgDQjybVU/mqdefault.jpg)
![Modernize Databases Faster with AI-Assisted Migration and Optimization
Database modernization has never had a magic button. Migrations can take weeks or months of converting code, resolving incompatibilities, and validating that applications still work as expected. AI is changing that. In this session, we’ll use Visual Studio Code, Microsoft Foundry, and GitHub Copilot to accelerate an end-to-end migration to PostgreSQL on Azure HorizonDB.
We’ll assess the existing application, convert schemas and SQL code, fix migration gaps, and progressively validate data, application logic, business behavior, and workloads.
Through a practical, end-to-end migration, we’ll show how AI can accelerate database modernization and help teams migrate faster and with greater confidence.
0:00 Introduction and Housekeeping
0:53 Speaker Introduction and Modernization Context
6:36 Microsoft Database Portfolio Overview
10:02 Modernizing Data with VS Code and GitHub Copilot
12:04 Azure Database for PostgreSQL and HorizonDB
13:12 VS Code Extension for PostgreSQL Features
15:52 Database Migration Process Overview
20:45 Behind the Scenes of the Migration Agent
22:31 Live Demo: Setting Up the Migration Project
24:42 Discovering Database Resources
27:10 Configuring the AI Model
28:35 Running the Schema Conversion
30:13 Deep Dive into Migration Instructions
33:14 Security and Private Endpoints
34:46 Summary of Supported and Unsupported Features
42:15 Application Migration with Copilot
47:05 Migrating Data and Validating Schemas
51:00 Performance and Cost Considerations
57:08 Wrap-Up and Next Steps
1:00:18 Validation and Post-Migration Query Demo
Check out the series - https://aka.ms/ModernizefasteSeries
[eventID:27666] Modernize Databases Faster with AI-Assisted Migration and Optimization](https://i.ytimg.com/vi/6-tkj3USlFg/mqdefault.jpg)
![Microsoft Fabric at Scale: Build, Deploy, and Govern (Option 1)
AI is changing what it means to build at scale. Microsoft Fabric brings development, deployment, security, and governance together so teams can move faster without losing control. See what a modern data foundation looks like when it’s built for today and ready for what AI makes possible next.
📌 This event is part of a series. Learn more here:
https://aka.ms/DataDays/FabConRecap/y
https://aka.ms/DataDays/IntoCerts/y
https://aka.ms/AIatWork/UnderstandIt/y
https://aka.ms/AIatWork/BuildIt/y
https://aka.ms/AIatWork/ShowIt/y
0:20 - Introduction and Housekeeping
1:26 - Welcome and Speaker Introductions
5:48 - AIs Impact on Data and Governance
11:45 - Tenant Administration and Governance
12:31 - Govern Experience Demo
19:11 - Network Security Overview
22:29 - Capacity Management and Billing
22:49 - Capacity Management Demo
28:19 - Item Creation Policies and Monitoring
35:40 - Observability and Monitoring Hub Demo
40:59 - Developer Experiences and Copilot
42:41 - Copilot Skills Demo
48:12 - Deployment Plans and Git Integration
54:43 - OneLake Catalog and Data Consumption
55:00 - OneLake Catalog Demo
59:21 - Closing Announcements and Resources
[eventID:27689] Microsoft Fabric at Scale: Build, Deploy, and Govern (Option 1)](https://i.ytimg.com/vi/6KTm_NHB9Gk/mqdefault.jpg)
![Episódio 3: Engenharia de Prompts com o Microsoft Copilot – Obtendo Melhores Resultados com IA
Aprenda técnicas práticas de engenharia de prompts e descubra como trabalhar de forma eficaz com o Microsoft Copilot. Esta sessão apresenta exemplos do mundo real que ajudarão os participantes a obter resultados gerados por IA mais precisos, relevantes e valiosos.
🔗 Aprenda mais acessando os recursos: https://aka.ms/conceitosdeIAdevs
📌 Este evento faz parte de uma série. Saiba mais aqui: https://aka.ms/aiskillsfortomorrow/pt-br/y
0:00 Introdução e conceitos básicos
4:12 Roteiro da apresentação
6:17 O que é Engenharia de Prompts
11:18 Anatomia de um prompt
16:30 Prompt Canvas (formato de briefing)
22:00 Demonstração: Resumo de reunião
29:25 Critérios de avaliação de respostas
33:05 Conversa interativa com a IA
37:45 Demonstração: Adaptação de conteúdo para diferentes públicos
42:58 Armadilhas comuns em prompts
47:50 Demonstração: Ciclo de escrita (rascunho, crítica, revisão)
55:35 Reuso e modelos de prompts
59:10 Recapitulação do ciclo de engenharia de prompts
#MicrosoftReactor #LearnConnectBuild #MicrosoftCopilot #Copilot #Agents #AIAgents #GenAI
[eventID:27644] Episódio 3: Engenharia de Prompts com o Microsoft Copilot – Obtendo Melhores Resultados com IA](https://i.ytimg.com/vi/6RWgB2HpFSY/mqdefault.jpg)
![Microsoft Foundry Hosted Agents with Microsoft Agent Framework
Learn how to build and deploy production-ready AI agents using Microsoft Agent Framework (MAF) and Microsoft Foundry.
In this hands-on session, well create agent workflows with MAF, package them as containerized applications, and deploy them as Foundry Hosted Agents with enterprise-grade security, scalability, and governance.
Youll see how to move from local development to production using Hosted Agents, agent protocols, and secure integrations.
0:00 Intro & Welcome
5:47 Overview of Building and Deploying Hosted Agents
7:06 Introduction to Microsoft Agent Framework
9:49 Agents vs. Workflows: When to Use Which
16:21 Introduction to Microsoft Foundry Platform
20:42 How Hosted Agents Work
24:34 Foundry Toolkit for VS Code Overview
26:45 Hands-on: Setting Up Foundry Resource
33:21 Hands-on: Building a Basic Agent in VS Code
44:48 Hands-on: Building a Stock Market Agent with Tools
53:07 Hands-on: Building a Multi-Agent Workflow
1:04:34 Testing the Multi-Agent System
1:07:15 Summary & Q&A
[eventID:27592] Microsoft Foundry Hosted Agents with Microsoft Agent Framework](https://i.ytimg.com/vi/6ZIx1lmpI2w/mqdefault.jpg)